Richard Socher launches Flint, an open-weights local coding model hitting 125+ tokens/s on a MacBook
RichardSocher · x · 2026-10-24
- Best-in-class fast local coding: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark, claimed up to 2x faster than comparable models
- Open weights already available on Hugging Face; runnable locally or free via opencode/pidot.dev
- Built from scratch in under 4 months by Recursive's automated research system, the Eureka Machine
- Quoted user John Langford reports it runs reasonably well on a home RTX 4090 (24GB): with the nvp4 version and CPU offloading of some layers, 50 tokens/s even after a 200k-token prefill
- Pitch: private, unmetered intelligence on your own machine
More from coding & agent
- TURTLE paper auto-evolves tool-use benchmarks, boosting hard tasks on AppWorld by 165% — MichaelD1729 · 2026-10-24
- Google's PLE benchmark: best AI agent scores only 50.6% on professional engineering deliverables — dair_ai · 2026-10-24
- LangChain fixed its design agent's AI slop with skills, a design wiki, and guardrails — LangChain · 2026-10-24
- Chronos: a Postgres-compatible database where agent changes land only if they pass your policies — Antique-Willow-5841 · 2026-10-24
- Agent sandbox boat.dev hits 1,026 paying subscribers with $20/mo per-second-billed VMs — ycombinator · 2026-10-24
- Claude Code Team OS: put your whole product team's context in one shared repo — aakashgupta · 2026-10-24